Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SethGammon/Citadel --skill daemongit clone --depth 1 https://github.com/SethGammon/CitadelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sethgammon/citadel/daemon)<a href="https://agentmods.dev/skills/sethgammon/citadel/daemon"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/daemon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sethgammon/citadel/daemon"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/daemon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.04277 |
| Opus 5.5 | $0.00028 | $0.01711 |
| Sonnet 5.5 | $0.00014 | $0.00855 |
| Haiku 4.5 | $0.00007 | $0.00428 |
Grade A, and why
daemon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/daemon -- Continuous Autonomous Operation
Architecture, daemon.json field reference, and rationale: docs/DAEMON.md.
Orientation
Use when: running campaigns overnight or unattended -- chains sessions automatically until a ceiling or budget is hit. Don't use when: a single autonomous session is enough (use /archon); you want manual control between cycles (use /loop).
Default execution path (READ FIRST)
/daemon start does NOT call RemoteTrigger by default. The local runner is the default. Only pass --remote to use Anthropic's routine system, and only after explicit user confirmation.
Why: RemoteTrigger counts against the account-wide 15 routine runs / 24h cap. A single overnight run can exhaust the quota and pause every other routine on the account (including unrelated ones). See docs/ROUTINE-QUOTA.md.
Default flow — /daemon start (no --remote flag)
- Do Steps 1, 2, and 4 below (validate, check existing, write
daemon.json). - Skip Step 3 — do NOT create any
RemoteTrigger. LeavechainTriggerIdandwatchdogTriggerIdasnullin the state file. - Instead of Step 5's trigger-confirmation, output the local-runner instructions (full text: docs/DAEMON.md#local-runner-default): the state file path, campaign, and budget, then:
To start the tick loop, run in a separate terminal: npm run daemon:local Leave that terminal open. It spawns `claude --permission-mode default -p "/do continue"` each session, respects daemon.json status, and consumes zero Anthropic routine quota. Stop with Ctrl+C or `/daemon stop`. For true unattended background operation (machine sleeps, user away): /daemon start --remote (uses RemoteTrigger, counts against 15/day cap)
Local execution safety
After approval of the campaign, finite budget and session limit, set
localRunnerEnabled: true in daemon.json for the local runner. The default
limit is 10 sessions; --max-sessions N requires a positive integer. A finite
positive budget and valid estimatedSpend are required. The runner stops on
failed execution and rechecks state before each spawn. Normal runtime permission
checks remain enabled. The noninteractive environment variable alone does not
authorize continuation. Remote starts leave this local opt-in disabled.
See runner safety and migration.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +12 lines 1d5e05d3f3b2
- 1mo ago First seen · 268 lines · 69 tokens per session scan A 65c227b7dfdc
daemon is a skill published in the GitHub repository SethGammon/Citadel (924 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 4,277 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
compose-org
Run a task as an evolved multi-agent ORG using the installed liquid-org framework — where YOU (the running Claude) embody the org: you ask liquid-org which proven team topology + specialist personas to use (retrieved from its evolved pool, or assembled fresh), then dispatch ONE SUBAGENT PER TALENT to play each role…
liquid-rank
Rank the available skills by RELEVANCE to the current task, on demand, using liquid-org's read-only hermes skill ranker. This is an EXPLICIT, OPT-IN selector you invoke WHEN you want help choosing the most relevant skill for what you're doing — it is NOT default, automatic skill selection, and it does NOT decide for…
present-gate
First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels. Invoke at the gate point after the FO has decided a stage must be presented.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
contexts
Use when the user says "get context on X", "how does X work", or wants architectural orientation before coding.